Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

AnnData Data Structure Skill

Teaches Claude the correct, up-to-date patterns for creating, reading, writing, concatenating and subsetting AnnData (.h5ad/zarr) objects in single-cell workflows.

Data & AnalyticsIntermediate★ 46,134⑂ 4,181AI score 8/10Last updated: Sep 21, 2026

What it does

  • Guides creation, reading and writing of AnnData objects across .h5ad, .zarr, CSV, MTX and Loom using current APIs (anndata.io).
  • Explains the object layout (X, obs, var, layers, obsm/varm, obsp/varp, uns, raw) and the view-vs-copy trap.
  • Provides concrete patterns for ad.concat batch merging (inner/outer joins, label/keys), backed mode and chunked processing for huge files, and memory optimization via sparse matrices and categoricals.
  • Steers away from deprecated APIs (ad.read, AnnData.concatenate(), __version__) and flags anndata.experimental as unstable.
  • Includes scverse ecosystem integration snippets for scanpy, muon and PyTorch (AnnLoader).

Who it's for

  • Bioinformaticians and grad students analyzing single-cell RNA-seq data in Python.
  • Anyone building scanpy/scvi-tools pipelines who keeps hitting data-format friction.
  • Users handling tens-to-hundreds of GB h5ad files under memory constraints.

Example uses

  1. "Merge batch1–batch3.h5ad with batch labels, keeping only shared genes" → generates ad.concat(..., label='batch', keys=[...], join='inner').
  2. "Extract cells with quality_score > 0.8 from a 100GB h5ad" → backed-mode read, filter, to_memory(), then write_h5ad(compression='gzip').
  3. "I keep running out of memory" → checklist of csr_matrix conversion, strings_to_categoricals(), and when to snapshot raw.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/anndata/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/anndata folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/anndata/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/anndata ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r scientific-agent-skills/skills/anndata ~/.claude/skills/
  4. Verify the bundled references/ markdown files came along: ls ~/.claude/skills/anndata
  5. Prepare a Python 3.11+ environment: uv pip install "anndata==0.12.16" (add scanpy if you need 10x readers).
  6. Restart Claude Code and try a prompt like "concatenate these h5ad files by batch" to confirm the skill triggers.
View source on GitHub ↗License: MIT